{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:44P6N2CAQKYEXRBR6VEXHFFTNB","short_pith_number":"pith:44P6N2CA","schema_version":"1.0","canonical_sha256":"e71fe6e84082b04bc431f5497394b3686e0904713da142c7352e2dea6f096f76","source":{"kind":"arxiv","id":"2506.01144","version":2},"attestation_state":"computed","paper":{"title":"FlowMo: Variance-Based Flow Guidance for Coherent Motion in Video Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ariel Shaulov, Hila Chefer, Itay Hazan, Lior Wolf","submitted_at":"2025-06-01T19:55:33Z","abstract_excerpt":"Text-to-video diffusion models are notoriously limited in their ability to model temporal aspects such as motion, physics, and dynamic interactions. Existing approaches address this limitation by retraining the model or introducing external conditioning signals to enforce temporal consistency. In this work, we explore whether a meaningful temporal representation can be extracted directly from the predictions of a pre-trained model without any additional training or auxiliary inputs. We introduce FlowMo, a novel training-free guidance method that enhances motion coherence using only the model's"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2506.01144","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-01T19:55:33Z","cross_cats_sorted":[],"title_canon_sha256":"9250d1d5941eb57db8fa8d5d0f05450cfd547c17ae530162a8985e1b1b385132","abstract_canon_sha256":"bf5f98cb52b4031f884ff0fd97d2ce189947b9d0ee52ee9886bca628d7118e1f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:47.598445Z","signature_b64":"TkXTWqjTImfQJUFSRScBqhyEQyJwEXlIqFH2Rqsg4skoW1y51zQMybPqrc+gzrIH3UEWEDVe51akycfrizKsBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e71fe6e84082b04bc431f5497394b3686e0904713da142c7352e2dea6f096f76","last_reissued_at":"2026-07-05T11:15:47.597805Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:47.597805Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FlowMo: Variance-Based Flow Guidance for Coherent Motion in Video Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ariel Shaulov, Hila Chefer, Itay Hazan, Lior Wolf","submitted_at":"2025-06-01T19:55:33Z","abstract_excerpt":"Text-to-video diffusion models are notoriously limited in their ability to model temporal aspects such as motion, physics, and dynamic interactions. Existing approaches address this limitation by retraining the model or introducing external conditioning signals to enforce temporal consistency. In this work, we explore whether a meaningful temporal representation can be extracted directly from the predictions of a pre-trained model without any additional training or auxiliary inputs. We introduce FlowMo, a novel training-free guidance method that enhances motion coherence using only the model's"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01144","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2506.01144/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2506.01144","created_at":"2026-07-05T11:15:47.597879+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.01144v2","created_at":"2026-07-05T11:15:47.597879+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01144","created_at":"2026-07-05T11:15:47.597879+00:00"},{"alias_kind":"pith_short_12","alias_value":"44P6N2CAQKYE","created_at":"2026-07-05T11:15:47.597879+00:00"},{"alias_kind":"pith_short_16","alias_value":"44P6N2CAQKYEXRBR","created_at":"2026-07-05T11:15:47.597879+00:00"},{"alias_kind":"pith_short_8","alias_value":"44P6N2CA","created_at":"2026-07-05T11:15:47.597879+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.01962","citing_title":"NeoMap: Training-free Novel-View Synthesis from Single Images and Videos","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11969","citing_title":"SpecLoR: Spectral Lookahead Rectification for Motion-Coherent Text-to-Video Generation","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2603.05539","citing_title":"VDCook:DIY video data cook your MLLMs","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/44P6N2CAQKYEXRBR6VEXHFFTNB","json":"https://pith.science/pith/44P6N2CAQKYEXRBR6VEXHFFTNB.json","graph_json":"https://pith.science/api/pith-number/44P6N2CAQKYEXRBR6VEXHFFTNB/graph.json","events_json":"https://pith.science/api/pith-number/44P6N2CAQKYEXRBR6VEXHFFTNB/events.json","paper":"https://pith.science/paper/44P6N2CA"},"agent_actions":{"view_html":"https://pith.science/pith/44P6N2CAQKYEXRBR6VEXHFFTNB","download_json":"https://pith.science/pith/44P6N2CAQKYEXRBR6VEXHFFTNB.json","view_paper":"https://pith.science/paper/44P6N2CA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.01144&json=true","fetch_graph":"https://pith.science/api/pith-number/44P6N2CAQKYEXRBR6VEXHFFTNB/graph.json","fetch_events":"https://pith.science/api/pith-number/44P6N2CAQKYEXRBR6VEXHFFTNB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/44P6N2CAQKYEXRBR6VEXHFFTNB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/44P6N2CAQKYEXRBR6VEXHFFTNB/action/storage_attestation","attest_author":"https://pith.science/pith/44P6N2CAQKYEXRBR6VEXHFFTNB/action/author_attestation","sign_citation":"https://pith.science/pith/44P6N2CAQKYEXRBR6VEXHFFTNB/action/citation_signature","submit_replication":"https://pith.science/pith/44P6N2CAQKYEXRBR6VEXHFFTNB/action/replication_record"}},"created_at":"2026-07-05T11:15:47.597879+00:00","updated_at":"2026-07-05T11:15:47.597879+00:00"}